Advanced Signal Processing Methods and Deep Neural Networks for Machine Fault Diagnosis

Dear Colleagues,

Signal processing algorithms and techniques are essential tools for conducting machinery fault diagnosis. Based on prior fault mechanisms, advanced signal processing methods are used to extract fault features from machine condition monitoring signals, such as temperature, pressure, vibration, and current. By constructing fault evaluation indicators, the operating status of the machine can be assessed, making it a common paradigm for machinery fault diagnosis. In recent years, with the emergence of deep learning theories and methods, various deep neural networks with different structures and functionalities have been introduced for analyzing the perception signals of machinery operation. Compared to the classical signal processing-based fault diagnosis paradigm, deep neural networks do not require prior knowledge of fault mechanisms. They can directly extract implicit fault features and identify the operating status of the machine from perception signals through supervised/unsupervised learning, thus achieving end-to-end intelligent diagnosis. As a purely data-driven diagnostic approach, deep neural networks sometimes lack interpretability in their mechanisms and output results. To address this issue, researchers have used classical signal processing theories to explain the working mechanisms and output results of neural networks, developing a series of interpretable deep neural networks.

This Special Issue aims to collect theoretical and applied research for diagnosis on advanced signal processing methods, deep neural networks, and interpretability of deep neural networks based on signal processing theory. Potential research topics include, but are not limited to, the following:

• Machinery fault mechanisms;
• Advanced signal processing methods and their applications in machinery fault diagnosis;
• Fault evaluation indicators;
• Deep neural network methods and their applications in machinery fault diagnosis;
• Interpretability of deep neural networks based on signal processing theory.

Dr. Shiqian Chen
Dr. Peng Zhou
Dr. Minghui Hu
Dr. Zhuyun Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machines is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.